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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 10895
    Prev
    Next
    INDEX
    Explanations

    discussions about social truths and resistance to commonly held beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.53
     secondaire
    -0.51
    openqa
    -0.51
    ]};
    -0.49
     ExecuteAsync
    -0.49
    cshtml
    -0.47
    igte
    -0.46
    })}\
    -0.45
     MonoBehaviour
    -0.45
    fony
    -0.45
    POSITIVE LOGITS
     uncomfortable
    0.86
    comfortable
    0.75
     discomfort
    0.73
     comfort
    0.71
     inconvenient
    0.71
     comfortable
    0.69
     admitir
    0.69
    Comfort
    0.67
     unwilling
    0.67
     Comfortable
    0.64
    Activations Density 0.342%

    No Known Activations