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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 7270
    Prev
    Next
    INDEX
    Explanations

    structured data entries associated with AWS roles and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.89
     ""],
    -0.79
    tvguidetime
    -0.76
    AndEndTag
    -0.75
     <>",
    -0.71
    }])
    -0.68
     Sociales
    -0.67
    '}}
    -0.67
    emang
    -0.67
    ufel
    -0.66
    POSITIVE LOGITS
    ::
    0.98
    Portale
    0.66
    protoimpl
    0.58
     ::
    0.58
    <b>
    0.57
    <strong>
    0.57
     مرئيه
    0.55
    ::_
    0.55
    __*/
    0.53
    fin
    0.49
    Activations Density 0.013%

    No Known Activations