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. 23-GEMMASCOPE-RES-16K
    6. 9226
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases and relational words indicative of reasoning or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    them
    -0.83
    ()]);
    -0.81
     ++;
    -0.77
    =?";
    -0.72
     THEM
    -0.70
    "}")
    -0.68
    ]++;
    -0.68
    him
    -0.64
    }`).
    -0.63
    ++];
    -0.63
    POSITIVE LOGITS
     although
    1.79
     despite
    1.60
     while
    1.55
     when
    1.51
     since
    1.47
     during
    1.41
     unlike
    1.36
     after
    1.34
    although
    1.32
     meskipun
    1.29
    Activations Density 1.577%

    No Known Activations