Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5583
    Prev
    Next
    INDEX
    Explanations

    references to contracts and financial transactions related to human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words that indicate enabling, facilitating, or being complicit in an action (e.g., verbs/nouns about helping, cooperating, or supporting wrongdoing or activities).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PasswordEncoder
    -0.46
     đa
    -0.44
    styleable
    -0.43
     waterfalls
    -0.42
    intracht
    -0.41
    equila
    -0.41
    bonucle
    -0.41
    Localisation
    -0.41
    getSimpleName
    -0.40
    spiegel
    -0.40
    POSITIVE LOGITS
    UnusedPrivate
    0.98
    -------------</
    0.81
     فريبيس
    0.72
     }}$}
    0.72
    EndContext
    0.71
    )++;
    0.71
    RenderAtEndOf
    0.71
    }}}
    
    0.67
    "]));
    0.67
    Portale
    0.66
    Activations Density 0.678%

    No Known Activations