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. 7-GEMMASCOPE-RES-16K
    6. 9415
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.79
     miſ
    -0.79
     raiſ
    -0.78
     purpoſe
    -0.75
    脚注の使い方
    -0.75
     ſever
    -0.74
     juſ
    -0.74
     Administrativna
    -0.72
     poffible
    -0.72
    )|^{
    -0.71
    POSITIVE LOGITS
    :
    0.71
     is
    0.66
    telar
    0.64
    的是
    0.63
     lautet
    0.59
     ialah
    0.57
     adalah
    0.56
     enten
    0.55
    的就是
    0.53
    toEqual
    0.52
    Activations Density 0.700%

    No Known Activations