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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14434
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions or factors that affect processes or systems

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

    Possessive pronouns: its, their

    np_acts-logits-general · gemini-2.0-flash

    possessive pronoun its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.57
     YOURSELF
    -0.52
    NSYLVANIA
    -0.49
    gew
    -0.49
     getItemCount
    -0.49
    arnia
    -0.47
    topt
    -0.46
    we
    -0.45
    writeFieldEnd
    -0.45
    yourself
    -0.44
    POSITIVE LOGITS
     its
    3.06
    Its
    2.31
     Its
    2.22
    its
    1.97
    其
    1.84
    它的
    1.60
     seus
    1.49
     suas
    1.49
     their
    1.48
     sua
    1.46
    Activations Density 0.940%

    No Known Activations