© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    buzzwords or strong statements in a list-like format

    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
    405
    +0.13
    0.4%
    1950
    +0.11
    0.4%
    662
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.13
    0.06
    662
    +0.11
    0.05
    1296
    +0.10
    0.05
    Negative Logits
    getLastName
    -0.65
     getCity
    -0.58
     getAge
    -0.53
    getFirstName
    -0.51
     StringUtil
    -0.50
     Warszawie
    -0.50
     getVersion
    -0.50
     getNombre
    -0.49
    getClassName
    -0.48
    getPhone
    -0.46
    POSITIVE LOGITS
    Get
    0.92
    get
    0.89
    GET
    0.86
     Get
    0.84
     GET
    0.84
     get
    0.83
    Gets
    0.82
     GETTING
    0.80
    getting
    0.77
    gets
    0.77
    Activations Density 0.175%

    No Known Activations