© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3822
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and search engines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.18
    0.6%
    678
    +0.13
    0.4%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.18
    0.07
    1870
    +0.13
    0.05
    505
    +0.12
    0.02
    Negative Logits
    <bos>
    -0.97
    GEBURTSDATUM
    -0.85
    ArgsConstructor
    -0.69
    UnitTesting
    -0.69
     autorytatywna
    -0.68
     Paglinawan
    -0.68
    BeginContext
    -0.67
    TemporalType
    -0.66
    BeforeClass
    -0.66
    SequentialGroup
    -0.66
    POSITIVE LOGITS
     „,
    1.46
     thut
    1.44
     doman
    1.44
     mef
    1.42
     gmbh
    1.41
     Intere
    1.41
     fta
    1.37
     Manufact
    1.37
     wien
    1.36
     kase
    1.35
    Activations Density 0.566%

    No Known Activations