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. 24-GEMMASCOPE-RES-16K
    6. 13916
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate attempts or efforts to do something

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    trying to + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    try
    -0.89
     try
    -0.87
    Try
    -0.85
     Try
    -0.82
    TypedDataSet
    -0.66
     want
    -0.64
    Ability
    -0.63
     Likely
    -0.62
     likely
    -0.62
    webElementXpaths
    -0.62
    POSITIVE LOGITS
     emulate
    0.61
     متعلقه
    0.59
     imitate
    0.59
     convince
    0.57
     persuade
    0.56
    IInterface
    0.55
    poons
    0.53
    RetentionPolicy
    0.53
     mimic
    0.53
     figure
    0.51
    Activations Density 0.180%

    No Known Activations